Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0002

Data Index: 347425 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1451116 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0670. Min Act: -0.0002

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0661. Min Act: -0.0002

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1276892 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0606. Min Act: -0.0002

Data Index: 949316 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0641. Min Act: -0.0002

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1191629 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0679. Min Act: -0.0002

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1407321 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0645. Min Act: -0.0002

Data Index: 959197 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0640. Min Act: -0.0002

Data Index: 377388 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1333143 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1483058 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1317592 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0623. Min Act: -0.0002

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0598. Min Act: -0.0002

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1065075 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0628. Min Act: -0.0002

Data Index: 443775 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0654. Min Act: -0.0002

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 113